CVE-2025-48956

HIGH EPSS 40.6%
Published Aug 21, 202510mo ago · Modified Jun 17, 20261w ago
7.5 CVSS 3.1
High
Find Similar
Published Aug 21, 2025 10mo ago
Last Modified Jun 17, 2026 1w ago

Description

vLLM is an inference and serving engine for large language models (LLMs). From 0.1.0 to before 0.10.1.1, a Denial of Service (DoS) vulnerability can be triggered by sending a single HTTP GET request with an extremely large header to an HTTP endpoint. This results in server memory exhaustion, potentially leading to a crash or unresponsiveness. The attack does not require authentication, making it exploitable by any remote user. This vulnerability is fixed in 0.10.1.1.

CVSS Details

Base Score
7.5
Exploitability
3.9
Impact
3.6
Vector string
CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:N/I:N/A:H
Attack Vector Network
Attack Complexity Low
Privileges Required None
User Interaction None
Scope Unchanged
Confidentiality None
Integrity None
Availability High

Threat Intelligence

EPSS Exploit Probability
40.6% percentile
Exploit & Patch Status
No Known Exploit
Patch Available

Weaknesses 1

CWE-400 Uncontrolled Resource Consumption Resource Mgmt

Affected Products 1

VendorProductVersionRange
vllmvllm*≥0.1.0  –  <0.10.1.1

References 3

  • github.com https://github.com/vllm-project/vllm/commit/d8b736f913a59117803d6701521d2e4861701944
    Patch
  • github.com https://github.com/vllm-project/vllm/pull/23267
    Issue TrackingPatch
  • github.com https://github.com/vllm-project/vllm/security/advisories/GHSA-rxc4-3w6r-4v47
    Vendor Advisory

Remediation

  • github.com https://github.com/vllm-project/vllm/commit/d8b736f913a59117803d6701521d2e4861701944
    Patch
  • github.com https://github.com/vllm-project/vllm/pull/23267
    Issue TrackingPatch